Small-Object Detection Based on YOLO and Dense Block via Image Super-Resolution

• Published in: IEEE access Vol. 9; pp. 56416 - 56429
• Main Authors: Wang, Zhuang-Zhuang, Xie, Kai, Zhang, Xin-Yu, Chen, Hua-Quan, Wen, Chang, He, Jian-Biao
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: balance loss function; Computer networks; Computer vision; dense block; Detectors; Feature extraction; foreground and background; Head; Image resolution; image super-resolution; multi-scale feature fusion; Object detection; Object recognition; Small-object detection; Superresolution; Target detection; Target recognition; Task analysis; Traffic signs; Training

Small-object detection is a basic and challenging problem in computer vision tasks. It is widely used in pedestrian detection, traffic sign detection, and other fields. This paper proposes a deep learning small-object detection method based on image super-resolution to improve the speed and accuracy...